Social network popularity prediction method and system based on high-order nonlinear dependency

Abstract

The invention discloses a social network popularity prediction method based on high-order nonlinear dependency, which comprises the following steps: obtaining and preprocessing topic related data, the topic related data comprising topic ranking and posting information; inputting the preprocessed data into the trained popularity prediction model, and outputting a topic popularity prediction result; wherein the training of the popularity prediction model comprises the following steps of: acquiring topic related data within a set time length and preprocessing the topic related data; calculating a high-order polynomial feature of the preprocessed historical sequence by using a Wollaston feature, and generating a multi-order tensor interaction feature; and setting a learnable discrete Wollaston coefficient matrix, independently carrying out polynomial integral modeling on each order of tensor interaction feature channel, carrying out linear aggregation on each channel output, and projecting the aggregated channel output to an original feature dimension space of an input time sequence to obtain a topic popularity prediction result.

Description

TECHNICAL FIELD

[0001] The application belongs to the technical field of social network analysis and complex system modeling, and particularly relates to a social network popularity prediction method and system based on high-order nonlinear dependence. BACKGROUND

[0002] Topic popularity prediction is an important research direction in social network analysis and computational social science. Existing research has made extensive studies on the popularity prediction problem in social networks and has achieved good results, but there are still many deficiencies.

[0003] Firstly, due to the large scale and complex structure of social networks, in the topic popularity prediction problem, a topic is usually related to a large number of posts, and its popularity is affected by a large number of post information. Existing research usually focuses on the popularity evolution process of a single post information in the social network, but cannot analyze the propagation of each related post one by one to predict the popularity of the topic.

[0004] Secondly, in social networks, the popularity of a topic is not only affected by post information, but also follows the natural evolution law of topics in social networks. External incentives and natural evolution are coupled, which makes it more difficult to model and predict the popularity of topics in social networks. Existing methods are difficult to model both factors, which hinders the further improvement of the accuracy of popularity prediction.

[0005] Finally, deep learning is the dominant method for modeling such complex time series data. However, current deep learning models usually perform as a black box, composed of linear and nonlinear functions, which cannot explicitly capture the inherent dynamic structure in real-world nonlinear systems, limiting their interpretability.

[0006] In summary, the main problems of existing models in topic popularity prediction include the large number of posts affecting the popularity of topics, and the popularity change is affected by many factors. These problems limit the effectiveness and interpretability of the model in practical applications, affecting the understanding and trust of users on the prediction results of the model. SUMMARY

[0007] To solve the problems that the existing model is limited by the number of posts affecting the popularity of the topic and the popularity change is affected by many factors in the prediction of the popularity of the topic, the application provides a social network popularity prediction method based on high-order nonlinear dependence, which is equivalent to a complex dynamic system by proposing a time series prediction model, and the macroscopic characteristics of the social network are realized by using the historical sampling data to describe the macroscopic characteristics of the social network. Under the guidance of this idea, the prediction of the popularity of the topic in the social network is regarded as an output prediction problem of a complex dynamic system under external excitation, and a polynomial integral network is used for modeling, so as to realize the prediction of the popularity of the topic and effectively improve the prediction accuracy.

[0008] According to an aspect of the application, a social network popularity prediction method based on high-order nonlinear dependence is provided, comprising: Obtaining and preprocessing topic-related data, wherein the topic-related data includes topic ranking and post information; Inputting the preprocessed data into the trained popularity prediction model to output the topic popularity prediction result; wherein the training of the popularity prediction model comprises: Obtaining and preprocessing the topic-related data within a set time period; Calculating the high-order polynomial features of the preprocessed historical sequence using Volterra features to generate multi-order tensor interaction features; Setting a learnable discrete Volterra coefficient matrix, independently modeling each order of tensor interaction feature channel with a polynomial integral, and projecting the linear aggregation of the output of each channel to the original feature dimension space of the input time sequence to obtain the topic popularity prediction result.

[0009] As a further technical solution, setting a learnable discrete Volterra coefficient matrix, independently modeling each order of feature channel with a polynomial integral, comprises: For the output of channel j The calculation process is: Wherein is a constant term, is a learnable coefficient matrix, is a Volterra feature, representing an n-order tensor interaction feature.

[0010] As a further technical solution, after obtaining the output of each channel, it further comprises: Using a linear transformation layer to splice the outputs of each channel together, and projecting the spliced output to the original feature dimension space of the input time sequence: , Wherein, W and b are learnable weight matrix and bias, represents the prediction result in the original space, represents the vector formed by concatenating all channel outputs at time t.

[0011] As a further technical solution, the Volterra characteristic is used to calculate the high-order polynomial characteristic of the historical sequence, including: The normalization operation is performed at each time point in the sequence respectively; The normalized sequence is flattened into a vector, and the i-th Kronecker product operation is used to generate , and then the Volterra characteristic is obtained.

[0012] As a further technical solution, the preprocessing includes: The topic-related data obtained is serialized; The serialized data is cleaned, and the abnormal value and missing value processing and normalization are performed.

[0013] According to an aspect of the present application, a social network popularity prediction system based on high-order nonlinear dependence is provided, including: A data preprocessing module for obtaining topic-related data and preprocessing, the topic-related data including topic ranking and post information; A popularity prediction module for inputting the preprocessed data into the trained popularity prediction model and outputting the topic popularity prediction result, the training of the popularity prediction module including: Obtaining the topic-related data within a set time period and preprocessing; Using the Volterra characteristic to calculate the high-order polynomial characteristic of the preprocessed historical sequence to generate a multi-order tensor interaction feature; Setting a learnable discrete Volterra coefficient matrix, modeling the polynomial integration of each order tensor interaction feature channel independently, projecting the linear aggregation of each channel output to the original feature dimension space of the input time sequence to obtain the topic popularity prediction result.

[0014] As a further technical solution, the popularity prediction module is also used to execute the following instructions: For the output of channel j , the calculation process is: , where is a constant term, is a learnable coefficient matrix, is a Volterra characteristic, representing an n-order tensor interaction feature.

[0015] As a further technical solution, the popularity prediction module is also used to execute the following instructions: A linear transformation layer is used to concatenate the outputs of each channel, and the concatenated output is projected onto the original feature dimension space of the input time series: , Where W and b are the learnable weight matrix and bias, This represents the predicted result of the original space. This represents the vector formed by concatenating the outputs of all channels at time t.

[0016] As a further technical solution, the popularity prediction module is also used to execute the following instructions: Perform normalization at each time point in the sequence; The normalized sequence is flattened into a vector, and then generated by i Kronecker product operations. Thus, the Volterra features were obtained. .

[0017] According to one aspect of the present invention, a non-transitory computer-readable storage medium is provided, the non-transitory computer-readable storage medium storing computer instructions that cause the computer to perform the aforementioned social network popularity prediction method based on higher-order nonlinear dependencies.

[0018] Compared with the prior art, the beneficial effects of the present invention are as follows: (1) Accurate prediction of topic popularity: The model of this invention can integrate the content characteristics and time series data of relevant posts, such as the number of reposts and comments, decouple the independent influence of natural evolution and external incentives, and achieve high-precision prediction of topic popularity by effectively utilizing relevant information.

[0019] (2) Model interpretability: This invention can not only make accurate predictions, but also intuitively express the relationships between variables. The model parameters can reflect the specific contribution and mutual influence of each variable to the prediction results, help users understand the internal mechanism of the model, and conduct detailed impact analysis on variables, quantifying the degree of influence of different variables on the predicted popularity of the topic.

[0020] (3) Proposal and Validation of the Prediction Model: This invention utilizes the variable relationships and influence analysis provided by the model to formulate a specific prediction scheme. By using historical relevant posting information and topic ranking data from the Weibo platform, the effectiveness of the model in predicting topic popularity is verified. The actual results are compared with the predicted results, for example... Figure 5 As shown. Attached Figure Description

[0021] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the accompanying drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the accompanying drawings described below are some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0022] Figure 1 This is a flowchart illustrating the social network popularity prediction method based on higher-order nonlinear dependencies provided in an embodiment of the present invention.

[0023] Figure 2 This is a schematic diagram of the training process of the popularity prediction model provided in an embodiment of the present invention.

[0024] Figure 3 This is a schematic diagram of the algorithm for the popularity prediction model provided in an embodiment of the present invention.

[0025] Figure 4 This is a structural block diagram of the popularity prediction model provided in an embodiment of the present invention.

[0026] Figure 5 This is a comparison chart of the predicted results and the actual results provided in the embodiments of the present invention. Detailed Implementation

[0027] The terms “comprising” and “having”, and any variations thereof, in the specification, claims, and accompanying drawings of this invention are intended to cover a non-exclusive inclusion, such as a process, method, system, product, or apparatus that includes a series of steps or units, not necessarily limited to those explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0028] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention. In addition, the technical features of the various embodiments or individual embodiments provided by the present invention can be arbitrarily combined to form new technical solutions. Such combinations are not bound by the order of steps and / or structural composition patterns, but must be based on the ability of those skilled in the art to implement them. When the combination of technical solutions is contradictory or cannot be implemented, it should be considered that such a combination of technical solutions does not exist and is not within the scope of protection claimed by the present invention.

[0029] Existing models for predicting topic popularity face several major challenges. These include the sheer number of posts influencing topic popularity and the multifaceted nature of popularity fluctuations. These issues limit the effectiveness and interpretability of these models in practical applications, impacting user understanding and trust in the prediction results. To address this, this invention provides a social network popularity prediction method based on high-order nonlinear dependencies. By treating topic popularity prediction in social networks as an output prediction problem of a complex dynamic system under external stimuli, and utilizing a multinomial integral network for modeling, this method accurately predicts the evolution of topic popularity under the influence of relevant posts. Furthermore, it details the natural evolution of topic popularity and its response to external posts, effectively improving the prediction accuracy for topic popularity.

[0030] This invention provides a method for predicting the popularity of social networks based on high-order nonlinear dependencies, such as... Figure 1 As shown, firstly, topic-related data is acquired and preprocessed, including topic rankings and posting information; then, the preprocessed data is input into the trained popularity prediction model, and the topic popularity prediction result is output.

[0031] The training of the popularity prediction model includes: Data preprocessing: Obtain topic-related data within a set time period and perform preprocessing; Multidimensional feature construction: Utilize Volterra features to calculate high-order polynomial features of the preprocessed historical sequence, generating multi-order tensor-quantized interaction features; Multi-channel linear transformation: A learnable discrete Volterra coefficient matrix is ​​set, and polynomial integral modeling is performed independently on each tensor interaction feature channel. The outputs of each channel are linearly aggregated and projected onto the original feature dimension space of the input time series to obtain the topic popularity prediction result.

[0032] The popularity prediction model provided by this invention aims to accurately predict the future popularity of topics and related posting information, intuitively express the relationship between variables, conduct detailed variable impact analysis, and provide effective system optimization strategies, thereby improving the accuracy of prediction and helping various organizations and individuals better understand the dynamics of social networks, thus making more informed choices in information dissemination, decision-making, and resource allocation.

[0033] First, such as Figure 2 and 3As shown, in the data preprocessing step, this embodiment of the invention preprocesses the topic-related data and then inputs it into the popularity prediction model. The topic-related data includes the number of reposts, comments, likes, whether it is a repost, sentiment score, and topic ranking. The popularity prediction model processes the topic-related data to predict the topic's popularity over a future period and the number of reposts and likes of future topic-related posts, among other important parameters.

[0034] Furthermore, the topic-related data is serialized, for example, the topic ranking is serialized to obtain... Where t is the length of the observed historical data, This is the ranking of topic popularity at time t. For example, it involves serializing other post information to obtain... Where t is the length of the observed historical data, and d is the dimension of each observation at time t. Let R represent the d-dimensional vector composed of the observations at time t, and let R represent the real number field.

[0035] It should be noted that after serializing the topic-related data, each feature sequence is a sequence of length T and dimension 1 with shape [T, 1]. D feature sequences are concatenated to form a multidimensional feature sequence with shape [T, D].

[0036] Preferably, the data preprocessing involves cleaning the input dataset, handling outliers and missing values ​​to ensure data quality, and normalizing the data to give it a more stable gradient and reduce the magnitude difference between features, thereby improving the accuracy of the model.

[0037] Next, in the multidimensional feature construction step, this embodiment of the invention utilizes Volterra features to calculate the high-order polynomial features of the historical sequence (i.e., the concatenated multidimensional feature sequence). For the input historical sequence, a normalization operation is performed on each time point t in the sequence from 0 to h-1, such that... ,here and These represent the mean and standard deviation used for data normalization, respectively. Next, we will discuss the normalized series. Flattened into a vector For i from 1 to k, let This step involves calculating the Kronecker product, where... This represents the Kronecker product operation, where `i` indicates performing the Kronecker product `i` times. Ultimately, it returns the Volterra feature. It represents the tensorized interaction of past states from order 1 to order k.

[0038] Then, in the multi-channel linear transformation step, for the already calculated multidimensional features... Each channel k independently models the nonlinear interactions and memory effects of the system. A learnable discrete Wolterra coefficient matrix is ​​set in each channel. To capture non-linear relationships.

[0039] Specifically, for the output of channel j The calculation process is as follows: ,in It is a constant term. It is a learnable coefficient matrix. This is a Volterra feature. After obtaining the output of each channel, a multi-channel linear transform layer is used to concatenate them together, and the output is projected back onto the original space: , ,in It is the number of channels. It is the dimension of the target time series. Indicates the first The output vectors of each channel at time t and , This represents the vector formed by concatenating the outputs of all channels at time t. and It consists of learnable weight matrices and biases.

[0040] Preferably, the multi-channel linear transformation layer uses polynomial approximation to provide a nonlinear representation of the latent function. Therefore, the method of the present invention does not depend on the activation function, does not require the design of a complex neural network structure, and only requires a simple linear layer to predict the coefficients of higher-order polynomials.

[0041] Preferably, the Volterra feature construction describes the matrix form polynomial expansion of the corresponding nonlinear dynamic system through the discrete Volterra coefficient matrix, thereby transforming the nonlinear problem of time series analysis into a linear problem of learning polynomial coefficients, improving the interpretability of the model. Furthermore, the multi-channel linear transformation provides a nonlinear representation of the latent function using polynomial approximation, without the need for activation functions, and learns high-order polynomial coefficients only through linear layers.

[0042] Preferably, the popularity prediction method effectively captures the complex spatiotemporal nonlinear interactions in dynamic systems by integrating high-order polynomials and time integrals into the neural network. This avoids the black box effect of traditional methods, improves the interpretability of the model, and makes it easier for users to understand the working principle of the model.

[0043] In this structure, the present invention calculates the discrete Vorterra coefficient matrix through polynomial expansion, transforming nonlinear time series modeling into linear polynomial coefficient learning. Then, a multi-channel linear layer is used to predict the discrete Vorterra coefficient matrix, obtaining an accurate prediction of topic popularity at future times. Experiments have proven the method to be valid and effective. By predicting topic popularity, the present invention can enhance the dynamic understanding of social networks, helping various organizations and individuals analyze the spread trends of topics on social networks, assisting users in formulating dissemination strategies in advance, and optimizing resource allocation.

[0044] The implementation of the various embodiments of the present invention is based on programmed processing through a device with processor functionality. Therefore, in practical engineering, the technical solutions and functions of the various embodiments of the present invention are encapsulated into various modules. Based on this reality, and building upon the above embodiments, the embodiments of the present invention provide a social network popularity prediction system based on higher-order nonlinear dependencies. This system is used to execute the social network popularity prediction method based on higher-order nonlinear dependencies in the above method embodiments.

[0045] like Figure 4 As shown, the system includes: a data preprocessing module for acquiring and preprocessing topic-related data, including topic rankings and posting information; and a popularity prediction module for inputting the preprocessed data into a trained popularity prediction model and outputting topic popularity prediction results. The training of the popularity prediction module includes: acquiring and preprocessing topic-related data within a set time period; calculating high-order polynomial features of the preprocessed historical sequence using Volterra features to generate multi-order tensor interaction features; setting a learnable discrete Volterra coefficient matrix; independently performing polynomial integral modeling on each order tensor interaction feature channel; linearly aggregating the outputs of each channel and projecting them onto the original feature dimension space of the input time series to obtain the topic popularity prediction results.

[0046] This invention provides a social network popularity prediction system based on high-order nonlinear dependencies. Addressing the limitations of existing models in predicting topic popularity due to the number of posts influencing topic popularity and the multifaceted impact of popularity changes, this system employs several modules and proposes a time-series prediction model. It treats the social network as a complex dynamic system, utilizing historical sampling data to characterize the macroscopic features of the social network. Guided by this idea, topic popularity prediction in a social network is viewed as the output prediction problem of a complex dynamic system under external stimuli, and modeled using a multinomial integral network, thereby achieving topic popularity prediction and effectively improving prediction accuracy.

[0047] It should be noted that the system embodiments provided by this invention, in addition to implementing the methods in the above method embodiments, are also used to implement the methods in other method embodiments provided by this invention. The difference lies only in setting corresponding functional modules, and their principles are basically the same as those of the above system embodiments provided by this invention. As long as those skilled in the art, based on the above system embodiments and referring to the specific technical solutions in other method embodiments, obtain corresponding technical means and technical solutions composed of these technical means by combining technical features, and improve the modules in the above system embodiments while ensuring the practicality of the technical solutions, they can obtain corresponding system-like embodiments for implementing the methods in other method-like embodiments. For example: Based on the above system embodiments, as a preferred embodiment, the social network popularity prediction system based on high-order nonlinear dependencies provided in this invention, wherein the data preprocessing module is further configured to execute the following instructions: The topic-related data is serialized, and the serialized data is then cleaned, outlier and missing value handled, and normalized.

[0048] Based on the above system embodiments, as a preferred embodiment, the social network popularity prediction system based on high-order nonlinear dependencies provided in this embodiment of the invention further includes, in the popularity prediction module: The multidimensional feature construction submodule calculates higher-order polynomial features from historical sequences and represents the multidimensional features as follows: These features represent from the first order to Tensor-quantized interactions of past states of different orders can capture complex dynamic information of different orders in time series.

[0049] Based on the above system embodiments, as a preferred embodiment, the social network popularity prediction system based on high-order nonlinear dependencies provided in this embodiment of the invention further includes, in the popularity prediction module: Multi-channel linear transformation submodule: By setting a learnable discrete coefficient matrix Each channel is independently modeled using polynomial integrals, effectively capturing the nonlinear interactions and memory effects of the system. The outputs from each independently modeled channel are then linearly aggregated and projected onto the original space, achieving the fusion of information from different channels. This captures the complex nonlinear dynamics and long-term dependencies in time series data, yielding prediction results and improving the model's ability to model and predict time series data.

[0050] Based on the same inventive concept as the foregoing embodiments, this embodiment of the invention also provides a non-transitory computer-readable storage medium storing computer instructions that cause the computer to execute the aforementioned social network popularity prediction method based on high-order nonlinear dependencies.

[0051] In summary, this invention discloses a social network popularity prediction method based on high-order nonlinear dependencies. A trained popularity prediction model is used to predict popularity over a future period. The model training includes: first, preprocessing topic-related data by serializing topic rankings and posting information (such as the number of reposts and comments), and performing data cleaning and normalization; then, calculating high-order polynomial features of historical sequences using a multi-dimensional feature construction module, and capturing tensor dynamic interactions from order 1 to k using Volterra features; finally, setting a learnable discrete coefficient matrix using a multi-channel linear transformation module, independently performing polynomial integral modeling for each channel, fusing multi-channel information, and projecting it onto the original space to generate prediction results, thus completing the training of the popularity prediction model. This invention constructs a neural network model of a complex dynamic system with multiple modules working together, enabling the model to effectively decouple the natural evolution of topic popularity from external stimuli, achieving high-precision prediction of topic popularity. It provides a feature representation with both high accuracy and interpretability for predicting topic propagation trends in social networks, and can be used in scenarios such as social network dynamic analysis and propagation strategy optimization.

[0052] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, and not to limit them; although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some or all of the technical features therein; and these modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the technical solutions of the embodiments of the present invention.

Claims

1. A social network popularity prediction method based on high-order nonlinear dependence, characterized in that, include: Acquire topic-related data within a set time period and preprocess it. The topic-related data includes topic rankings and posting information. The preprocessed data is input into the trained popularity prediction model, which outputs the topic popularity prediction results for a preset future time period; wherein, the training of the popularity prediction model includes: Acquire topic-related data within a set time period and preprocess it; We use Volterra features to calculate high-order polynomial features of the preprocessed historical sequence and generate multi-order tensor-quantized interaction features. We set up a learnable discrete Volterra coefficient matrix, independently modeled the interaction feature channels of each order of tensor quantization using polynomial integrals, and projected the linearly aggregated outputs of each channel onto the original feature dimension space of the input time series to obtain the topic popularity prediction results.

2. The social network popularity prediction method based on high-order nonlinear dependence according to claim 1, characterized in that, Set up a learnable discrete Volterra coefficient matrix and perform independent multinomial integral modeling for each order of feature channel, including: For the output of channel j The calculation process is as follows: ,in It is a constant term. It is a learnable coefficient matrix. It is a Volterra feature, representing the nth-order tensor interaction feature.

3. The social network popularity prediction method based on high-order nonlinear dependence according to claim 2, characterized in that, After obtaining the output of each channel, it also includes: A linear transformation layer is used to concatenate the outputs of each channel, and the concatenated output is projected onto the original feature dimension space of the input time series: ， Where W and b are the learnable weight matrix and bias, This represents the predicted result of the original space. This represents the vector formed by concatenating the outputs of all channels at time t.

4. The social network popularity prediction method based on high-order nonlinear dependence according to claim 1, characterized in that, Calculating higher-order polynomial features of historical sequences using Volterra features includes: Perform normalization at each time point in the sequence; The normalized sequence is flattened into a vector, and then generated by i Kronecker product operations. Thus, the Volterra features were obtained. .

5. The social network popularity prediction method based on high-order nonlinear dependence according to claim 1, characterized in that, The preprocessing includes: The acquired topic-related data is serialized; The serialized data is cleaned, outliers and missing values ​​are handled, and normalization is performed.

6. A social network popularity prediction system based on high-order nonlinear dependencies, characterized in that, include: The data preprocessing module is used to acquire and preprocess topic-related data, including topic rankings and posting information. The popularity prediction module is used to input preprocessed data into the trained popularity prediction model and output the topic popularity prediction result. The training of the popularity prediction module includes: Acquire topic-related data within a set time period and preprocess it; We use Volterra features to calculate high-order polynomial features of the preprocessed historical sequence and generate multi-order tensor-quantized interaction features. We set up a learnable discrete Volterra coefficient matrix, independently modeled the interaction feature channels of each order of tensor quantization using polynomial integrals, and projected the linearly aggregated outputs of each channel onto the original feature dimension space of the input time series to obtain the topic popularity prediction results.

7. The social network popularity prediction system based on high-order nonlinear dependence according to claim 6, characterized in that, The popularity prediction module is also used to execute the following instructions: For the output of channel j The calculation process is as follows: ,in It is a constant term. It is a learnable coefficient matrix. It is a Volterra feature, representing the nth-order tensor interaction feature.

8. The social network popularity prediction system based on high-order nonlinear dependence according to claim 7, characterized in that, The popularity prediction module is also used to execute the following instructions: A linear transformation layer is used to concatenate the outputs of each channel, and the concatenated output is projected onto the original feature dimension space of the input time series: ， Where W and b are the learnable weight matrix and bias, This represents the predicted result of the original space. This represents the vector formed by concatenating the outputs of all channels at time t.

9. The social network popularity prediction system based on high-order nonlinear dependence according to claim 6, characterized in that, The popularity prediction module is also used to execute the following instructions: Perform normalization at each time point in the sequence; The normalized sequence is flattened into a vector, and then generated by i Kronecker product operations. Thus, the Volterra features were obtained. .

10. A non-transitory computer-readable storage medium, characterized in that, The non-transitory computer-readable storage medium stores computer instructions that cause the computer to perform the social network popularity prediction method based on higher-order nonlinear dependencies as described in any one of claims 1 to 5.

Images